Implementation of hand geometry: an analysis of user perspectives and system performance

This discusses the implementation issues of installing a commercially available hand geometry system in the current infrastructure of Purdue University's Recreational Sports Center. In addition to a performance analysis of the system, a pre- and post-data collection survey was distributed to the 129 test subjects gathering information on perceptions of biometrics, in particular hand geometry, as well as participants' thoughts and feelings during their interaction with the hand geometry device. The results of the survey suggest that participants were accepting of hand geometry. Additionally, analyses of the participants' survey responses revealed that 93% liked using hand geometry, 98% thought it was easy to use, and 87% preferred it to the existing card-based system, while nobody thought the device invaded their personal privacy. System performance achieved a 3-try match rate of 99.02% (FRR 0.98%) when "gaming"/potential impostor attempts were removed from analysis. The failure to enroll rate was zero. Statistical analyses exposed a significant difference in the scores of attempts made by users with prior hand geometry usage, and subjects that could not straighten out their hand on the device. However, there were no statistical difference in the effects of rings/no rings, improper hand placements/proper hand placements, or gender on hand geometry score.     

Evaluation of a facial recognition algorithm across three illumination conditions

This work evaluated the performance of a commercially available face recognition algorithm for the verification of an individual's identity pertaining to three enrollment illumination levels. Existing facial recognition technology from still or video sources is becoming a practical tool for law enforcement, security, and counter-terrorist applications despite the limitations of the current technology. At this time, facial recognition has been implemented in limited applications, but has not been exhaustively studied in adverse conditions, which has initiated continuing study aimed at improving algorithms to compare images or representations of images to recognize a suspect (Paul, 2002). Moreover, this evaluation examined the influence of variations in illumination levels on the performance of a face recognition algorithm, specifically testing the significance between verification attempts and enrollment conditions with respect to factors of age, gender, ethnicity, facial characteristics, and facial obstructions. The results of this evaluation showed that for low and medium illuminance enrollments, there was a statistically significant difference between verification attempts made at low, medium, and high illuminance. However, for the high illuminance enrollment, there was no statistically significant difference between verification attempts made at low, medium, or high illuminance. Furthermore, this evaluation showed that the enrollment illumination level is a better indicator of the verification rate than the verification illumination level.